| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-eurosat-50/checkpoint-495", | |
| "epoch": 30.0, | |
| "global_step": 1650, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.228915662650602e-06, | |
| "loss": 1.9251, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.4457831325301205e-05, | |
| "loss": 1.5952, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6693181818181818, | |
| "eval_loss": 0.848971426486969, | |
| "eval_runtime": 10.9926, | |
| "eval_samples_per_second": 80.054, | |
| "eval_steps_per_second": 5.003, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 2.168674698795181e-05, | |
| "loss": 1.1596, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.891566265060241e-05, | |
| "loss": 0.8796, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.967453733248245e-05, | |
| "loss": 0.7582, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8386363636363636, | |
| "eval_loss": 0.45608994364738464, | |
| "eval_runtime": 11.0458, | |
| "eval_samples_per_second": 79.668, | |
| "eval_steps_per_second": 4.979, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 2.929164007657945e-05, | |
| "loss": 0.5899, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 2.8908742820676455e-05, | |
| "loss": 0.4953, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 2.852584556477345e-05, | |
| "loss": 0.4359, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9227272727272727, | |
| "eval_loss": 0.24076080322265625, | |
| "eval_runtime": 10.9212, | |
| "eval_samples_per_second": 80.577, | |
| "eval_steps_per_second": 5.036, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 2.8142948308870455e-05, | |
| "loss": 0.4, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 2.7760051052967455e-05, | |
| "loss": 0.361, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2.7377153797064455e-05, | |
| "loss": 0.318, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9568181818181818, | |
| "eval_loss": 0.12942154705524445, | |
| "eval_runtime": 11.0819, | |
| "eval_samples_per_second": 79.409, | |
| "eval_steps_per_second": 4.963, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 2.6994256541161455e-05, | |
| "loss": 0.2481, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 2.6611359285258455e-05, | |
| "loss": 0.2414, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.990909090909091, | |
| "eval_loss": 0.03464468568563461, | |
| "eval_runtime": 11.2055, | |
| "eval_samples_per_second": 78.533, | |
| "eval_steps_per_second": 4.908, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 2.622846202935546e-05, | |
| "loss": 0.2313, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 2.5845564773452456e-05, | |
| "loss": 0.2074, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 2.546266751754946e-05, | |
| "loss": 0.1888, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9863636363636363, | |
| "eval_loss": 0.04186202958226204, | |
| "eval_runtime": 11.0353, | |
| "eval_samples_per_second": 79.744, | |
| "eval_steps_per_second": 4.984, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 2.507977026164646e-05, | |
| "loss": 0.2057, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 2.469687300574346e-05, | |
| "loss": 0.1693, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 2.431397574984046e-05, | |
| "loss": 0.1717, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9943181818181818, | |
| "eval_loss": 0.023813609033823013, | |
| "eval_runtime": 11.0829, | |
| "eval_samples_per_second": 79.402, | |
| "eval_steps_per_second": 4.963, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 2.393107849393746e-05, | |
| "loss": 0.1614, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 2.3548181238034463e-05, | |
| "loss": 0.1525, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.316528398213146e-05, | |
| "loss": 0.1785, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9943181818181818, | |
| "eval_loss": 0.023027343675494194, | |
| "eval_runtime": 11.2031, | |
| "eval_samples_per_second": 78.55, | |
| "eval_steps_per_second": 4.909, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 2.2782386726228464e-05, | |
| "loss": 0.1256, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 2.2399489470325464e-05, | |
| "loss": 0.1654, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.007612039800733328, | |
| "eval_runtime": 11.1318, | |
| "eval_samples_per_second": 79.053, | |
| "eval_steps_per_second": 4.941, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 2.2016592214422464e-05, | |
| "loss": 0.1437, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 2.1633694958519464e-05, | |
| "loss": 0.1363, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 2.1250797702616464e-05, | |
| "loss": 0.1322, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.004579578526318073, | |
| "eval_runtime": 11.0656, | |
| "eval_samples_per_second": 79.526, | |
| "eval_steps_per_second": 4.97, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 10.18, | |
| "learning_rate": 2.0867900446713468e-05, | |
| "loss": 0.1242, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 2.0485003190810464e-05, | |
| "loss": 0.1121, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 2.0102105934907468e-05, | |
| "loss": 0.1123, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.003508554305881262, | |
| "eval_runtime": 10.9833, | |
| "eval_samples_per_second": 80.122, | |
| "eval_steps_per_second": 5.008, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "learning_rate": 1.9719208679004468e-05, | |
| "loss": 0.1192, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 1.9336311423101468e-05, | |
| "loss": 0.1179, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 1.8953414167198468e-05, | |
| "loss": 0.0953, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.002522848779335618, | |
| "eval_runtime": 11.0556, | |
| "eval_samples_per_second": 79.598, | |
| "eval_steps_per_second": 4.975, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "learning_rate": 1.8570516911295472e-05, | |
| "loss": 0.1302, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 12.73, | |
| "learning_rate": 1.818761965539247e-05, | |
| "loss": 0.0864, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0033287114929407835, | |
| "eval_runtime": 11.1101, | |
| "eval_samples_per_second": 79.207, | |
| "eval_steps_per_second": 4.95, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 13.09, | |
| "learning_rate": 1.780472239948947e-05, | |
| "loss": 0.1334, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 1.7421825143586472e-05, | |
| "loss": 0.0769, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 1.7038927887683472e-05, | |
| "loss": 0.0984, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9988636363636364, | |
| "eval_loss": 0.003271339228376746, | |
| "eval_runtime": 11.0383, | |
| "eval_samples_per_second": 79.723, | |
| "eval_steps_per_second": 4.983, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "learning_rate": 1.6656030631780472e-05, | |
| "loss": 0.0932, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 1.6273133375877472e-05, | |
| "loss": 0.079, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 14.91, | |
| "learning_rate": 1.5890236119974476e-05, | |
| "loss": 0.0952, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.001456564525142312, | |
| "eval_runtime": 10.9322, | |
| "eval_samples_per_second": 80.496, | |
| "eval_steps_per_second": 5.031, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 1.5507338864071473e-05, | |
| "loss": 0.087, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 15.64, | |
| "learning_rate": 1.5124441608168476e-05, | |
| "loss": 0.0879, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 1.4741544352265476e-05, | |
| "loss": 0.0678, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0022302898578345776, | |
| "eval_runtime": 11.0758, | |
| "eval_samples_per_second": 79.453, | |
| "eval_steps_per_second": 4.966, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 16.36, | |
| "learning_rate": 1.4358647096362477e-05, | |
| "loss": 0.0687, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 16.73, | |
| "learning_rate": 1.3975749840459477e-05, | |
| "loss": 0.0592, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0012722605606541038, | |
| "eval_runtime": 10.904, | |
| "eval_samples_per_second": 80.704, | |
| "eval_steps_per_second": 5.044, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 17.09, | |
| "learning_rate": 1.3592852584556478e-05, | |
| "loss": 0.0701, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "learning_rate": 1.3209955328653479e-05, | |
| "loss": 0.0952, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 17.82, | |
| "learning_rate": 1.2827058072750479e-05, | |
| "loss": 0.0729, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9988636363636364, | |
| "eval_loss": 0.00370142818428576, | |
| "eval_runtime": 11.1436, | |
| "eval_samples_per_second": 78.969, | |
| "eval_steps_per_second": 4.936, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "learning_rate": 1.2444160816847479e-05, | |
| "loss": 0.0841, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 18.55, | |
| "learning_rate": 1.206126356094448e-05, | |
| "loss": 0.0837, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 18.91, | |
| "learning_rate": 1.167836630504148e-05, | |
| "loss": 0.0672, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.9988636363636364, | |
| "eval_loss": 0.004141129087656736, | |
| "eval_runtime": 11.0993, | |
| "eval_samples_per_second": 79.284, | |
| "eval_steps_per_second": 4.955, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 19.27, | |
| "learning_rate": 1.1295469049138481e-05, | |
| "loss": 0.0572, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 19.64, | |
| "learning_rate": 1.0912571793235483e-05, | |
| "loss": 0.0577, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.0529674537332483e-05, | |
| "loss": 0.0615, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.001032730215229094, | |
| "eval_runtime": 11.0623, | |
| "eval_samples_per_second": 79.55, | |
| "eval_steps_per_second": 4.972, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 20.36, | |
| "learning_rate": 1.0146777281429485e-05, | |
| "loss": 0.0546, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 20.73, | |
| "learning_rate": 9.763880025526483e-06, | |
| "loss": 0.058, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0008914543432183564, | |
| "eval_runtime": 10.9202, | |
| "eval_samples_per_second": 80.585, | |
| "eval_steps_per_second": 5.037, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 21.09, | |
| "learning_rate": 9.380982769623483e-06, | |
| "loss": 0.0497, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 21.45, | |
| "learning_rate": 8.998085513720485e-06, | |
| "loss": 0.0538, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 21.82, | |
| "learning_rate": 8.615188257817485e-06, | |
| "loss": 0.0571, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9988636363636364, | |
| "eval_loss": 0.002123360289260745, | |
| "eval_runtime": 10.9798, | |
| "eval_samples_per_second": 80.147, | |
| "eval_steps_per_second": 5.009, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 22.18, | |
| "learning_rate": 8.232291001914487e-06, | |
| "loss": 0.0636, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 22.55, | |
| "learning_rate": 7.849393746011487e-06, | |
| "loss": 0.0365, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 22.91, | |
| "learning_rate": 7.466496490108488e-06, | |
| "loss": 0.0755, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.9988636363636364, | |
| "eval_loss": 0.002230195328593254, | |
| "eval_runtime": 11.0651, | |
| "eval_samples_per_second": 79.529, | |
| "eval_steps_per_second": 4.971, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 23.27, | |
| "learning_rate": 7.083599234205488e-06, | |
| "loss": 0.0763, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 23.64, | |
| "learning_rate": 6.700701978302489e-06, | |
| "loss": 0.0547, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 6.317804722399489e-06, | |
| "loss": 0.0688, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9988636363636364, | |
| "eval_loss": 0.0025376665871590376, | |
| "eval_runtime": 10.9568, | |
| "eval_samples_per_second": 80.315, | |
| "eval_steps_per_second": 5.02, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 24.36, | |
| "learning_rate": 5.93490746649649e-06, | |
| "loss": 0.0726, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 24.73, | |
| "learning_rate": 5.5520102105934905e-06, | |
| "loss": 0.0417, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.00029166368767619133, | |
| "eval_runtime": 11.0108, | |
| "eval_samples_per_second": 79.922, | |
| "eval_steps_per_second": 4.995, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 25.09, | |
| "learning_rate": 5.1691129546904915e-06, | |
| "loss": 0.0472, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 25.45, | |
| "learning_rate": 4.7862156987874925e-06, | |
| "loss": 0.0565, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 25.82, | |
| "learning_rate": 4.4033184428844934e-06, | |
| "loss": 0.0589, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0006550709367729723, | |
| "eval_runtime": 10.9639, | |
| "eval_samples_per_second": 80.264, | |
| "eval_steps_per_second": 5.016, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 26.18, | |
| "learning_rate": 4.020421186981493e-06, | |
| "loss": 0.0452, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 26.55, | |
| "learning_rate": 3.6375239310784937e-06, | |
| "loss": 0.0587, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 26.91, | |
| "learning_rate": 3.2546266751754947e-06, | |
| "loss": 0.0563, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0006738207302987576, | |
| "eval_runtime": 10.975, | |
| "eval_samples_per_second": 80.182, | |
| "eval_steps_per_second": 5.011, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 27.27, | |
| "learning_rate": 2.8717294192724956e-06, | |
| "loss": 0.0441, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 27.64, | |
| "learning_rate": 2.4888321633694958e-06, | |
| "loss": 0.0401, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 2.1059349074664967e-06, | |
| "loss": 0.0603, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9988636363636364, | |
| "eval_loss": 0.0009842341532930732, | |
| "eval_runtime": 10.951, | |
| "eval_samples_per_second": 80.358, | |
| "eval_steps_per_second": 5.022, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 28.36, | |
| "learning_rate": 1.723037651563497e-06, | |
| "loss": 0.0417, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 28.73, | |
| "learning_rate": 1.3401403956604976e-06, | |
| "loss": 0.0469, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0004589582094922662, | |
| "eval_runtime": 10.9725, | |
| "eval_samples_per_second": 80.2, | |
| "eval_steps_per_second": 5.013, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 29.09, | |
| "learning_rate": 9.572431397574984e-07, | |
| "loss": 0.0518, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 29.45, | |
| "learning_rate": 5.743458838544991e-07, | |
| "loss": 0.0446, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 29.82, | |
| "learning_rate": 1.914486279514997e-07, | |
| "loss": 0.0525, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.00037947672535665333, | |
| "eval_runtime": 10.9402, | |
| "eval_samples_per_second": 80.438, | |
| "eval_steps_per_second": 5.027, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "step": 1650, | |
| "total_flos": 2.4304114274567455e+19, | |
| "train_loss": 0.19108782262513133, | |
| "train_runtime": 4786.2205, | |
| "train_samples_per_second": 22.051, | |
| "train_steps_per_second": 0.345 | |
| } | |
| ], | |
| "max_steps": 1650, | |
| "num_train_epochs": 30, | |
| "total_flos": 2.4304114274567455e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |